Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization 文章

ArXiv CS.AI2026-06-02NEWSen作者: Mingyi Wang, Zhuoer Shen, Yuheng Bu, Shaofeng Zou
查看原文 →
关系图谱

Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization · 相关技术

相关技术

GRPOLagrangian primal-dual reinforcement learning algorithmAI-text detectorsConstrained Markov Decision ProcessesDetector Evasion Policy Optimization